CVE-2026-22778PYSEC-2026-565GHSA-4R2X-XPJR-7CVV
vLLM leaks a heap address when PIL throws an error
- Published
- Last modified
- Where the record stands: published, rejected by its publisher, or superseded by another id.What do these mean? →
- published
- Whether CISA lists it in its Known Exploited Vulnerabilities catalog: proof that attackers are using it.What do these mean? →
- Not listed in CISA KEV
- Fix
- Fixed in 0.14.1
- Whether working attack code is public (Exploit-DB, Metasploit, Nuclei or GitHub). Public code makes attacks easier.What do these mean? →
- 1 Metasploit module, 1 proof of concept on GitHub, 1 Nuclei template
CISA's decision points: whether it is exploited, whether attacks can be automated, and how much control an attacker gets. Assessed (SSVC 2.0.3).What do these mean? →
- Exploitation: none
- Automatable: yes
- Technical impact: total
Summary
vLLM is an inference and serving engine for large language models (LLMs). From 0.8.3 to before 0.14.1, when an invalid image is sent to vLLM's multimodal endpoint, PIL throws an error. vLLM returns this error to the client, leaking a heap address. With this leak, we reduce ASLR from 4 billion guesses to ~8 guesses. This vulnerability can be chained a heap overflow with JPEG2000 decoder in OpenCV/FFmpeg to achieve remote code execution. This vulnerability is fixed in 0.14.1.
Timeline
- CVE published
- CISA SSVC assessment
Exploitation: none · Automatable: yes · Technical impact: total
- Record last updated
- EPSS reached 10%
FIRST estimates at least a 10% chance of exploitation in the next 30 days
Affected versions
- vllm-project vllm
From 0.8.3 · fixed in 0.14.1
- vllmPyPI
From 0.8.3 · fixed in 0.14.1